© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207498
    Prev
    Next
    INDEX
    Explanations

    SVG code

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    最后一
    0.42
    :^(
    0.42
     orthogonal
    0.40
    ыз
    0.40
     callSettings
    0.40
    orthogonal
    0.39
     tacked
    0.39
    蛞
    0.39
     sitä
    0.39
     nvp
    0.38
    POSITIVE LOGITS
    Thought
    0.40
    hound
    0.39
    Dre
    0.39
    toi
    0.38
    letto
    0.37
     years
    0.37
    獵
    0.37
     calendars
    0.37
    Times
    0.36
    Stress
    0.36
    Activations Density 0.000%

    No Known Activations